تهدف هذه الورقة إلى تقديم نظرة عامة شاملة للتطورات الأخيرة في تتبع حكمة الحوار (DST) لأنظمة المحادثات الموجهة نحو المهام.نقدم المهمة، وخاصة البيانات الرئيسية التي تم استغلالها وكذلك مقاييس تقييمها، ونحن نحلل العديد من النهج المقترحة.نحن نميز بين نماذج DST غير الثابتة، والتي تتنبأ بمجموعة ثابتة من دول الحوار، ونماذج الأطباق الديناميكية، والتي يمكن أن تتنبؤ حوار الحوار حتى عندما تتغير عملية الأونولوجيا.ونناقش أيضا قدرة النموذج على تتبع النطاقات الفردية أو المتعددة والقياس إلى مجالات جديدة، سواء من حيث نقل المعرفة والتعلم الصفر.نحن نغطي فترة من عام 2013 إلى 2020، مما يدل على زيادة كبيرة في أساليب مجال متعددة، ومعظمها باستخدام نماذج اللغة المدربة مسبقا.
This paper aims at providing a comprehensive overview of recent developments in dialogue state tracking (DST) for task-oriented conversational systems. We introduce the task, the main datasets that have been exploited as well as their evaluation metrics, and we analyze several proposed approaches. We distinguish between static ontology DST models, which predict a fixed set of dialogue states, and dynamic ontology models, which can predict dialogue states even when the ontology changes. We also discuss the model's ability to track either single or multiple domains and to scale to new domains, both in terms of knowledge transfer and zero-shot learning. We cover a period from 2013 to 2020, showing a significant increase of multiple domain methods, most of them utilizing pre-trained language models.
References used
https://aclanthology.org/
Continual learning in task-oriented dialogue systems allows the system to add new domains and functionalities overtime after deployment, without incurring the high cost of retraining the whole system each time. In this paper, we propose a first-ever
Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot fillin
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the cross-task knowledge from genera
Frame-based state representation is widely used in modern task-oriented dialog systems to model user intentions and slot values. However, a fixed design of domain ontology makes it difficult to extend to new services and APIs. Recent work proposed to
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge. However, in real scenarios, domain knowledge is subject to